
I’m a PhD candidate at the MIT Computer Science & Artificial Intelligence Lab (CSAIL), where I am a member of the Laboratory of Financial Engineering advised by Professor Andrew W. Lo. My research is supported by the MIT Presidential Fellowship and the Mathworks Engineering Fellowship. I’ve also been fortunate to spend time at J.P. Morgan, BlueCove Limited, and Replicate.
I have a SM in Computer Science from MIT and a BS in Computer Science and Philosophy from Columbia Engineering. While I was an undergraduate at Columbia, I worked on problems in multimodal deep learning with Professor Carl Vondrick. I was also involved in the entrepreneurial ecosystem on campus.
I work on deploying large language models in finance. I focus on evaluating and post-training LLMs as financial experts, designing effective ways for people and LLMs to work together on financial decisions, and studying the broader effects of using LLMs in finance:
Shen, Shannon Zejiang, Valerie Chen, Ken Gu, Alexis Ross, Zixian Ma, Jillian Ross, Alex Gu, Chenglei Si, Wayne Chi, Andi Peng, Jocelyn J. Shen, Ameet Talwalkar, Tongshuang Wu, and David Sontag (2025), Task Completion Agents are Not Ideal Collaborators
NeurIPS Workshop on Socially Responsible and Trustworthy Foundation Models (Best Paper)
[arXiv] [Website]
Renda, Alana, Jillian Ross, Michael Cafarella, and Jacob Andreas (2025), OpenEstimate: Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data
International Conference on Learning Representations (ICLR)
[arXiv]
Lo, Andrew W., and Jillian Ross (2025), My Co-Pilot, My Friend: Large Language Models and Fiduciary Duty
Revue d’Économie Financière (No. 159), Association d’Économie Financière
[Book]
Lo, Andrew W., and Jillian Ross (2024), Generative AI from Theory to Practice: A Case Study of Financial Advice
An MIT Exploration of Generative AI
[MIT Press]
Lo, Andrew W., and Jillian Ross (2024), Can ChatGPT Plan Your Retirement?: Generative AI and Financial Advice
Harvard Data Science Review (Special Issue 5)
[HDSR] [Press]
Ross, Jillian, Yoon Kim, and Andrew W. Lo (2024), LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory
Conference on Language Modeling (COLM)
[arXiv]
Send me an email:
[firstname] [at] csail [dot] mit [dot] edu